arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.15429eess.IVcs.CV
收藏

在50万张胸部X光片中寻找气胸

Searching for Pneumothorax in Half a Million Chest X-Ray Images

University of Waterloo(滑铁卢大学);Vector Institute(向量研究所)

Antonio Sze-To, Hamid Tizhoosh

摘要:

气胸,一个塌陷或下降的肺,是一个致命的条件,通常发现胸部X光由一个有经验的放射科医生。由于缺乏这样的专家,已经开发了基于深度神经网络的自动检测系统。然而,在实践中应用这些系统仍然是一个挑战。这些系统,主要计算一个单一的概率作为输出,可能不足以诊断。相反,基于内容的医学图像检索(CBIR)系统,如图像搜索,可以帮助临床医生进行诊断,使他们能够比较他们正在检查的情况下,与以前的(已经诊断)的情况。然而,目前对这种尝试的研究还比较缺乏。在这项研究中,我们探讨了使用图像搜索来分类气胸的胸部X线图像。所有的胸部X光图像都首先使用深度预训练的特征进行标记,这些特征是从现有的深度学习模型中获得的。给定查询胸部X射线图像,然后将前K个检索图像的多数投票用作分类器,其中除了概率输出之外还提供过去病例档案中的类似病例。在我们的实验中,从三个最近发布的大型公共数据集中获得了551,383张胸部X射线图像。使用10倍交叉验证,结果表明,与在相同特征上训练的传统分类器相比,在深度预训练特征上的图像搜索取得了令人满意的结果。据了解,这是第一项证明深度预训练特征可用于50万张胸部X射线图像中气胸CBIR的研究。

英文摘要:

Pneumothorax, a collapsed or dropped lung, is a fatal condition typically detected on a chest X-ray by an experienced radiologist. Due to shortage of such experts, automated detection systems based on deep neural networks have been developed. Nevertheless, applying such systems in practice remains a challenge. These systems, mostly compute a single probability as output, may not be enough for diagnosis. On the contrary, content-based medical image retrieval (CBIR) systems, such as image search, can assist clinicians for diagnostic purposes by enabling them to compare the case they are examining with previous (already diagnosed) cases. However, there is a lack of study on such attempt. In this study, we explored the use of image search to classify pneumothorax among chest X-ray images. All chest X-ray images were first tagged with deep pretrained features, which were obtained from existing deep learning models. Given a query chest X-ray image, the majority voting of the top K retrieved images was then used as a classifier, in which similar cases in the archive of past cases are provided besides the probability output. In our experiments, 551,383 chest X-ray images were obtained from three large recently released public datasets. Using 10-fold cross-validation, it is shown that image search on deep pretrained features achieved promising results compared to those obtained by traditional classifiers trained on the same features. To the best of knowledge, it is the first study to demonstrate that deep pretrained features can be used for CBIR of pneumothorax in half a million chest X-ray images.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑